Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / chinesehuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,273.97 rating
Confidence interval: 1,262.75 – 1,285.19
5932 votes
Category
chinese
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,254.61 rating
Confidence interval: 1,245.70 – 1,263.51
8138 votes
Category
coding
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,284.03 rating
Confidence interval: 1,274.23 – 1,293.83
7025 votes
Category
creative_writing
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,281.55 rating
Confidence interval: 1,275.53 – 1,287.57
26318 votes
Category
english
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,203.13 rating
Confidence interval: 1,195.85 – 1,210.41
34077 votes
Category
exclude_ties
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,214.85 rating
Confidence interval: 1,200.52 – 1,229.17
2449 votes
Category
expert
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,306.61 rating
Confidence interval: 1,280.54 – 1,332.69
754 votes
Category
french
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,274.80 rating
Confidence interval: 1,257.28 – 1,292.32
1779 votes
Category
german
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,248.05 rating
Confidence interval: 1,240.83 – 1,255.26
14100 votes
Category
hard_prompts
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
gemini-advanced-0514
1,249.17 rating
Confidence interval: 1,240.49 – 1,257.85
8405 votes
Category
hard_prompts_english
Evaluated configuration
gemini-advanced-0514
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating